Stars
Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞
An AI-powered security review GitHub Action using Claude to analyze code changes for security vulnerabilities.
Bash is all you need - A nano claude code–like 「agent harness」, built from 0 to 1
Trae Agent is an LLM-based agent for general purpose software engineering tasks.
A neurosymbolic framework for vulnerability detection in code
Production-ready platform for agentic workflow development.
Validate and visualize dependencies. Your rules. JavaScript, TypeScript, CoffeeScript. ES6, CommonJS, AMD.
Use PageRank to find the most important files in your codebase.
📦 Repomix is a powerful tool that packs your entire repository into a single, AI-friendly file. Perfect for when you need to feed your codebase to Large Language Models (LLMs) or other AI tools lik…
Benchmark ClassEval for class-level code generation.
[TMLR] A curated list of language modeling researches for code (and other software engineering activities), plus related datasets.
Official repo of VLABench, a large scale benchmark designed for fairly evaluating VLA, Embodied Agent, and VLMs.
Open-source code analysis platform for C/C++/Java/Binary/Javascript/Python/Kotlin based on code property graphs. Discord https://discord.gg/vv4MH284Hc
The official Python library for the OpenAI API
Open-source AI orchestration framework for building context-engineered, production-ready LLM applications. Design modular pipelines and agent workflows with explicit control over retrieval, routing…
A manually vetted dataset for security vulnerability detection in Java projects
Zero shot vulnerability discovery using LLMs
Android open source project analysis. Note: The project has been moved to https://github.com/BeesAndroid/BeesAndroid.
Repository for the paper "Large Language Model-Based Agents for Software Engineering: A Survey". Keep updating.
本项目旨在分享大模型相关技术原理以及实战经验（大模型工程化、大模型应用落地）
The fundamental package for scientific computing with Python.
scikit-learn: machine learning in Python
🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.